Microwave Breast Sensing via Deep Learning for Tumor Spatial Localization by Probability Maps.

BACKGROUND: microwave imaging (MWI) has emerged as a promising modality for breast cancer screening, offering cost-effective, rapid, safe and comfortable exams. However, the practical application of MWI for tumor detection and localization is hampered by its inherent low resolution and low detection capability. METHODS: this study aims to generate an accurate tumor probability map directly from the scattering matrix. This direct conversion makes the probability map independent of specific image formation techniques and thus potentially complementary to any image formation technique. An approach based on a convolutional neural network (CNN) is used to convert the scattering matrix into a tumor probability map. The proposed deep learning model is trained using a large realistic numerical dataset of two-dimensional (2D) breast slices. The performance of the model is assessed through visual inspection and quantitative measures to assess the predictive quality at various levels of detail. RESULTS: the results demonstrate a remarkably high accuracy (0.9995) in classifying profiles as healthy or diseased, and exhibit the model's ability to accurately locate the core of a single tumor (within 0.9 cm for most cases). CONCLUSION: overall, this research demonstrates that an approach based on neural networks (NN) for direct conversion from scattering matrices to tumor probability maps holds promise in advancing state-of-the-art tumor detection algorithms in the MWI domain.

A Deep Learning Approach for Diagnosis Support in Breast Cancer Microwave Tomography.

In this paper, a deep learning technique for tumor detection in a microwave tomography framework is proposed. Providing an easy and effective imaging technique for breast cancer detection is one of the main focuses for biomedical researchers. Recently, microwave tomography gained a great attention due to its ability to reconstruct the electric properties maps of the inner breast tissues, exploiting nonionizing radiations. A major drawback of tomographic approaches is related to the inversion algorithms, since the problem at hand is nonlinear and ill-posed. In recent decades, numerous studies focused on image reconstruction techniques, in same cases exploiting deep learning. In this study, deep learning is exploited to provide information about the presence of tumors based on tomographic measures. The proposed approach has been tested with a simulated database showing interesting performances, in particular for scenarios where the tumor mass is particularly small. In these cases, conventional reconstruction techniques fail in identifying the presence of suspicious tissues, while our approach correctly identifies these profiles as potentially pathological. Therefore, the proposed method can be exploited for early diagnosis purposes, where the mass to be detected can be particularly small.

An End-to-End Deep Learning Approach for Quantitative Microwave Breast Imaging in Real-Time Applications.

(1) Background: In this paper, an artificial neural network approach for effective and real-time quantitative microwave breast imaging is proposed. It proposes some numerical analyses for the optimization of the network architecture and the improvement of recovery performance and processing time in the microwave breast imaging framework, which represents a fundamental preliminary step for future diagnostic applications. (2) Methods: The methodological analysis of the proposed approach is based on two main aspects: firstly, the definition and generation of a proper database adopted for the training of the neural networks and, secondly, the design and analysis of different neural network architectures. (3) Results: The methodology was tested in noisy numerical scenarios with different values of SNR showing good robustness against noise. The results seem very promising in comparison with conventional nonlinear inverse scattering approaches from a qualitative as well as a quantitative point of view. (4) Conclusion: The use of quantitative microwave imaging and neural networks can represent a valid alternative to (or completion of) modern conventional medical imaging techniques since it is cheaper, safer, fast, and quantitative, thus suitable to assist medical decisions.

An Experimental Ultrasound System for Qualitative Tomographic Imaging.

The advancement of new promising techniques in the field of biomedical imaging has always been paramount for the research community. Recently, ultrasound tomography has proved to be a good candidate for non-invasive and safe diagnostics. In particular, breast cancer imaging may benefit from this approach, as frequent screening and early diagnosis require decreased system size and costs compared to conventional imaging techniques. Furthermore, a major advantage of these approaches consists in the operator-independent feature, which is very desirable compared to conventional hand-held ultrasound imaging. In this framework, the authors present some imaging results on an experimental campaign acquired via an in-house ultrasound tomographic system designed and built at the University of Naples Parthenope. Imaging performance was evaluated via different tests, showing good potentiality in structural information retrieval. This study represents a first proof of concept in order to validate the system and to consider further realistic cases in near future applications.

Detection of Cross-Frequency Coupling Between Brain Areas: An Extension of Phase Linearity Measurement.

The current paper proposes a method to estimate phase to phase cross-frequency coupling between brain areas, applied to broadband signals, without any a priori hypothesis about the frequency of the synchronized components. N:m synchronization is the only form of cross-frequency synchronization that allows the exchange of information at the time resolution of the faster signal, hence likely to play a fundamental role in large-scale coordination of brain activity. The proposed method, named cross-frequency phase linearity measurement (CF-PLM), builds and expands upon the phase linearity measurement, an iso-frequency connectivity metrics previously published by our group. The main idea lies in using the shape of the interferometric spectrum of the two analyzed signals in order to estimate the strength of cross-frequency coupling. We first provide a theoretical explanation of the metrics. Then, we test the proposed metric on simulated data from coupled oscillators synchronized in iso- and cross-frequency (using both Rössler and Kuramoto oscillator models), and subsequently apply it on real data from brain activity. Results show that the method is useful to estimate n:m synchronization, based solely on the phase of the signals (independently of the amplitude), and no a-priori hypothesis is available about the expected frequencies.

Hand Gesture Signatures Acquisition and Processing by Means of a Novel Ultrasound System.

Hand gestures represent a natural way to express concepts and emotions which are peculiar to each culture. Several studies exploit biometric traits, such as fingerprint, iris or face for subject identification purposes. Within this paper, a novel ultrasound system for person identification that exploits hand gestures is presented. The system works as a sonar, measuring the ultrasonic pressure waves scattered by the subject's hand, and analysing its Doppler information. Further, several transformations for obtaining time/frequency representations of the acquired signal are computed and a deep learning detector is implemented. The proposed system is cheap, reliable, contactless and can be easily integrated with other personal identification approaches allowing different security levels. The performances are evaluated via experimental tests carried out on a group of 25 volunteers. Results are encouraging, showing the promising potential of the system.

Flexible brain dynamics underpins complex behaviours as observed in Parkinson's disease.

Rapid reconfigurations of brain activity support efficient neuronal communication and flexible behaviour. Suboptimal brain dynamics is associated to impaired adaptability, possibly leading to functional deficiencies. We hypothesize that impaired flexibility in brain activity can lead to motor and cognitive symptoms of Parkinson's disease (PD). To test this hypothesis, we studied the 'functional repertoire'-the number of distinct configurations of neural activity-using source-reconstructed magnetoencephalography in PD patients and controls. We found stereotyped brain dynamics and reduced flexibility in PD. The intensity of this reduction was proportional to symptoms severity, which can be explained by beta-band hyper-synchronization. Moreover, the basal ganglia were prominently involved in the abnormal patterns of brain activity. Our findings support the hypotheses that: symptoms in PD relate to impaired brain flexibility, this impairment preferentially involves the basal ganglia, and beta-band hypersynchronization is associated with reduced brain flexibility. These findings highlight the importance of extensive functional repertoires for correct behaviour.

Neuronal Avalanches to Study the Coordination of Large-Scale Brain Activity: Application to Rett Syndrome.

Many complex systems, such as the brain, display large-scale coordinated interactions that create ordered patterns. Classically, such patterns have been studied using the framework of criticality, i.e., at a transition point between two qualitatively distinct patterns. This kind of system is generally characterized by a scale-invariant organization, in space and time, optimally described by a power-law distribution whose slope is quantified by an exponent α. The dynamics of these systems is characterized by alternating periods of activations, called avalanches, with quiescent periods. To maximize its efficiency, the system must find a trade-off between its stability and ease of propagation of activation, which is achieved by a branching process. It is quantified by a branching parameter σ defined as the average ratio between the number of activations in consecutive time bins. The brain is itself a complex system and its activity can be described as a series of neuronal avalanches. It is known that critical aspects of brain dynamics are modeled with a branching parameter σ = , and the neuronal avalanches distribution fits well with a power law distribution exponent α = -3/2. The aim of our work was to study a self-organized criticality system in which there was a change in neuronal circuits due to genetic causes. To this end, we have compared the characteristics of neuronal avalanches in a group of 10 patients affected by Rett syndrome, during an open-eye resting-state condition estimated using magnetoencephalography, with respect to 10 healthy subjects. The analysis was performed both in broadband and in the five canonical frequency bands. We found, for both groups, a branching parameter close to 1. In this critical condition, Rett patients show a lower distribution parameter α in the delta and broadband. These results suggest that the large-scale coordination of activity occurs to a lesser extent in RTT patients.

An extension of Phase Linearity Measurement for revealing cross frequency coupling among brain areas.

BACKGROUND: Brain areas need to coordinate their activity in order to enable complex behavioral responses. Synchronization is one of the mechanisms neural ensembles use to communicate. While synchronization between signals operating at similar frequencies is fairly straightforward, the estimation of synchronization occurring between different frequencies of oscillations has proven harder to capture. One specifically hard challenge is to estimate cross-frequency synchronization between broadband signals when no a priori hypothesis is available about the frequencies involved in the synchronization. METHODS: In the present manuscript, we expand upon the phase linearity measurement, an iso-frequency synchronization metrics previously developed by our group, in order to provide a conceptually similar approach able to detect the presence of cross-frequency synchronization between any components of the analyzed broadband signals. RESULTS: The methodology has been tested on both synthetic and real data. We first exploited Gaussian process realizations in order to explore the properties of our new metrics in a synthetic case study. Subsequently, we analyze real source-reconstructed data acquired by a magnetoencephalographic system from healthy controls in a clinical setting to study the performance of our metrics in a realistic environment. CONCLUSIONS: In the present paper we provide an evolution of the PLM methodology able to reveal the presence of cross-frequency synchronization between broadband data.

An automated magnetoencephalographic data cleaning algorithm.

The problem of cleaning magnetoencephalographic data is addressed in this manuscript. At present, several denoising procedures have been proposed in the literature, nevertheless their adoption is limited due to the difficulty in implementing and properly tuning the algorithms. Therefore, as of today, the gold standard remains manual cleaning. We propose an approach developed with the aim of automating each step of the manual cleaning. Its peculiarities are the ease of implementation and using and the remarkable reproducibility of the results. Interestingly, the algorithm has been designed to imitate the reasoning behind the manual procedure, carried out by trained experts. Our statistical analysis shows that no significant differences can be found between the two approaches.

Mutations in the SPAST gene causing hereditary spastic paraplegia are related to global topological alterations in brain functional networks.

AIM: Our aim was to describe the rearrangements of the brain activity related to genetic mutations in the SPAST gene. METHODS: Ten SPG4 patients and ten controls underwent a 5 min resting state magnetoencephalography recording and neurological examination. A beamformer algorithm reconstructed the activity of 90 brain areas. The phase lag index was used to estimate synchrony between brain areas. The minimum spanning tree was used to estimate topological metrics such as the leaf fraction (a measure of network integration) and the degree divergence (a measure of the resilience of the network against pathological events). The betweenness centrality (a measure to estimate the centrality of the brain areas) was used to estimate the centrality of each brain area. RESULTS: Our results showed topological rearrangements in the beta band. Specifically, the degree divergence was lower in patients as compared to controls and this parameter related to clinical disability. No differences appeared in leaf fraction nor in betweenness centrality. CONCLUSION: Mutations in the SPAST gene are related to a reorganization of the brain topology.

Phase Linearity Measurement: A Novel Index for Brain Functional Connectivity.

The problem of describing how different brain areas interact between each other has been granted a great deal of attention in the last years. The idea that neuronal ensembles behave as oscillators and that they communicate through synchronization is now widely accepted. To this regard, EEG and MEG provide the signals that allow the estimation of such communication in vivo. Hence, phase-based metrics are essential. However, the application of phased-based metrics for measuring brain connectivity has proved problematic so far, since they appear to be less resilient to noise as compared to amplitude-based ones. In this paper, we address the problem of designing a purely phase-based brain connectivity metric, insensitive to volume conduction and resilient to noise. The proposed metric, named phase linearity measurement (PLM), is based on the analysis of similar behaviors in the phases of the recorded signals. The PLM is tested in two simulated datasets as well as in real MEG data acquired at the Naples MEG center. Due to its intrinsic characteristics, the PLM shows considerable noise rejection properties as compared to other widely adopted connectivity metrics. We conclude that the PLM might be valuable in order to allow better estimation of phase-based brain connectivity.

Denoising of MR images using Kolmogorov-Smirnov distance in a Non Local framework.

Data coming from any acquisition system, such as Magnetic Resonance Imaging ones, are affected by noise. Although modern high field scanners can reach high Signal to Noise Ratios, in some circumstances, for example in case of very weak signals due to a specific acquisition sequence, noise becomes a critical issue that has to be properly handled. In the last years methods based on the so called Non Local Mean have proven to be very effective in denoising tasks. The idea of these filters is to find similar patches across the image and to jointly exploit them to obtain the restored image. A critical point is the distance metric adopted for measuring similarity. Within this manuscript, we propose a filtering technique based on the Kolmogorov-Smirnov distance. The main innovative aspect of the proposed method consists of the criteria adopted for finding similar pixels across the image: it is based on the statistics of the points rather than the widely adopted weighted Euclidean distance. More in details, the Cumulative Distribution Functions of different pixels are evaluated and compared in order to measure their similarities, exploiting a stack of images of the same slice acquired with different acquisition parameters. To quantitatively and qualitatively assess the performances of the approach, a comparison with other widely adopted denoising filters in case of both simulated and real datasets has been carried out. The obtained results confirm the validity of the proposed solution.

Amnestic Mild Cognitive Impairment Is Associated With Frequency-Specific Brain Network Alterations in Temporal Poles.

There is general agreement that the neuropathological processes leading to Alzheimer's disease (AD) begin decades before the clinical onset. In order to detect early topological changes, we applied functional connectivity and network analysis to magnetoencephalographic (MEG) data obtained from 16 patients with amnestic Mild Cognitive Impairment (aMCI), a prodromal stage of AD, and 16 matched healthy control (HCs). Significant differences between the two groups were found in the theta band, which is associated with memory processes, in both temporal poles (TPs). In aMCI, the degree and betweenness centrality (BC) were lower in the left superior TP, whereas in the right middle TP the BC was higher. A statistically significant negative linear correlation was found between the BC of the left superior TP and a delayed recall score, a sensitive marker of the "hippocampal memory" deficit in early AD. Our results suggest that the TPs, which are involved early in AD pathology and belong to the memory circuitry, have an altered role in the functional network in aMCI.

KSR-NLM: a non local means despeckling filter for ultrasound images based on ratio patch and KS distance.

Speckle noise greatly degrades the quality of ultrasound images. Being signal dependent, it requires the design of specific filters in order to be reduce. Within this manuscript, $a$ novel approach for despeckling ultrasound images is proposed. The methodology belongs to the Non Local Means family. The novelty consists in the methodology adopted for measuring patches similarity. In brief, the statistical distribution of the ratio image patch is estimated and compared to the theoretical Cumulative Distribution Function. More in detail, the Kolmogorov-Smirnov distance is adopted for measuring the similarity between the two distribution. The method, namely KSR-NLM, has shown to achieve good denoising performances both in case of synthetic and real datasets.

Brain functional networks become more connected as amyotrophic lateral sclerosis progresses: a source level magnetoencephalographic study.

This study hypothesizes that the brain shows hyper connectedness as amyotrophic lateral sclerosis (ALS) progresses. 54 patients (classified as "early stage" or "advanced stage") and 25 controls underwent magnetoencephalography and MRI recordings. The activity of the brain areas was reconstructed, and the synchronization between them was estimated in the classical frequency bands using the phase lag index. Brain topological metrics such as the leaf fraction (number of nodes with degree of 1), the degree divergence (a measure of the scale-freeness) and the degree correlation (a measure of disassortativity) were estimated. Betweenness centrality was used to estimate the centrality of the brain areas. In all frequency bands, it was evident that, the more advanced the disease, the more connected, scale-free and disassortative the brain networks. No differences were evident in specific brain areas. Such modified brain topology is sub-optimal as compared to controls. Within this framework, our study shows that brain networks become more connected according to disease staging in ALS patients.

Correction: Rucco, R.; et al. Type and Location of Wearable Sensors for Monitoring Falls during Static and Dynamic Tasks in Healthy Elderly: A Review. Sensors 2018, 18, 1613.

The authors wish to make a correction to their paper [1]. The following Table 1 should be replaced with the table shown below it[...].

Type and Location of Wearable Sensors for Monitoring Falls during Static and Dynamic Tasks in Healthy Elderly: A Review.

In recent years, the meaning of successful living has moved from extending lifetime to improving the quality of aging, mainly in terms of high cognitive and physical functioning together with avoiding diseases. In healthy elderly, falls represent an alarming accident both in terms of number of events and the consequent decrease in the quality of life. Stability control is a key approach for studying the genesis of falls, for detecting the event and trying to develop methodologies to prevent it. Wearable sensors have proved to be very useful in monitoring and analyzing the stability of subjects. Within this manuscript, a review of the approaches proposed in the literature for fall risk assessment, fall prevention and fall detection in healthy elderly is provided. The review has been carried out by using the most adopted publication databases and by defining a search strategy based on keywords and boolean algebra constructs. The analysis aims at evaluating the state of the art of such kind of monitoring, both in terms of most adopted sensor technologies and of their location on the human body. The review has been extended to both dynamic and static analyses. In order to provide a useful tool for researchers involved in this field, the manuscript also focuses on the tests conducted in the analyzed studies, mainly in terms of characteristics of the population involved and of the tasks used. Finally, the main trends related to sensor typology, sensor location and tasks have been identified.

Mindfulness Meditation Is Related to Long-Lasting Changes in Hippocampal Functional Topology during Resting State: A Magnetoencephalography Study.

It has been suggested that the practice of meditation is associated to neuroplasticity phenomena, reducing age-related brain degeneration and improving cognitive functions. Neuroimaging studies have shown that the brain connectivity changes in meditators. In the present work, we aim to describe the possible long-term effects of meditation on the brain networks. To this aim, we used magnetoencephalography to study functional resting-state brain networks in Vipassana meditators. We observed topological modifications in the brain network in meditators compared to controls. More specifically, in the theta band, the meditators showed statistically significant (p corrected = 0.009) higher degree (a centrality index that represents the number of connections incident upon a given node) in the right hippocampus as compared to controls. Taking into account the role of the hippocampus in memory processes, and in the pathophysiology of Alzheimer's disease, meditation might have a potential role in a panel of preventive strategies.

Enhanced Wiener filter for ultrasound image restoration.

BACKGROUND AND OBJECTIVE: Speckle phenomenon strongly affects UltraSound (US) images. In the last years, several efforts have been done in order to provide an effective denoising methodology. Although good results have been achieved in terms of noise reduction effectiveness, most of the proposed approaches are not characterized by low computational burden and require the supervision of an external operator for tuning the input parameters. METHODS: Within this manuscript, a novel approach is investigated, based on Wiener filter. Working in the frequency domain, it is characterized by high computational efficiency. With respect to classical Wiener filter, the proposed Enhanced Wiener filter is able to locally adapt itself by tuning its kernel in order to combine edges and details preservation with effective noise reduction. This characteristic is achieved by implementing a Local Gaussian Markov Random Field for modeling the image. Due to its intrinsic characteristics, the computational burden of the algorithm is sensibly low compared to other widely adopted filters and the parameter tuning effort is minimal, being well suited for quasi real time applications. RESULTS: The approach has been tested on both simulated and real datasets, showing interesting performances compared to other state of art methods. CONCLUSIONS: A novel denoising method for UltraSound images is proposed. The approach is able to combine low computational burden with interesting denoising performances and details preservation.